VerifAI用可验证机制减少生物医学问答中的幻觉，提升答案可信度。
VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering
- 将答案拆解为原子命题，用微调NLI模型逐条验证证据
- 在HealthVer基准上优于GPT-4，显著减少虚构引用
- 模块化设计，支持透明溯源，适合医疗等高风险场景
我们提出VerifAI，一个开源的生物医学问答专家系统，融合检索增强生成（RAG）与新型事后声明验证机制。不同于常规RAG系统，VerifAI通过将生成答案分解为原子命题，并利用微调的自然语言推理（NLI）引擎对照检索证据进行验证，确保事实一致性。系统包含三个模块：（1）针对生物医学查询优化的混合信息检索（IR）模块，MAP@10达42.7%；（2）基于自建数据集微调的引用感知生成组件，输出带参考的答案；（3）检测幻觉的验证组件，在HealthVer基准上表现超越GPT-4。评估显示，VerifAI相比零样本基线显著减少幻觉引用，并为每个命题提供可追溯的证据链。完整流程（含代码、模型、数据集）已开源，助力高风险领域中可靠AI部署。
原文摘要 · Abstract (English)
We introduce VerifAI, an open-source expert system for biomedical question answering that integrates retrieval-augmented generation (RAG) with a novel post-hoc claim verification mechanism. Unlike standard RAG systems, VerifAI ensures factual consistency by decomposing generated answers into atomic claims and validating them against retrieved evidence using a fine-tuned natural language inference (NLI) engine. The system comprises three modular components: (1) a hybrid Information Retrieval (IR) module optimized for biomedical queries (MAP@10 of 42.7%), (2) a citation-aware Generative Component fine-tuned on a custom dataset to produce referenced answers, and (3) a Verification Component that detects hallucinations with state-of-the-art accuracy, outperforming GPT-4 on the HealthVer benchmark. Evaluations demonstrate that VerifAI significantly reduces hallucinated citations compared to zero-shot baselines and provides a transparent, verifiable lineage for every claim. The full pipeline, including code, models, and datasets, is open-sourced to facilitate reliable AI deployment in high-stakes domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。